Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1786 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.8715. Min Act: -0.0003

Data Index: 767940 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.8547. Min Act: -0.0002

Data Index: 365382 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.7599. Min Act: -0.0002

Data Index: 978484 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.7804. Min Act: -0.0002

Data Index: 673136 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.7415. Min Act: -0.0002

Data Index: 242827 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.7413. Min Act: -0.0002

Data Index: 210302 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.7206. Min Act: -0.0002

Data Index: 455554 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6812. Min Act: -0.0002

Data Index: 1305242 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6715. Min Act: -0.0002

Data Index: 1067172 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.7087. Min Act: -0.0002

Data Index: 549960 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6751. Min Act: -0.0002

Data Index: 174523 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6263. Min Act: -0.0002

Data Index: 233511 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6669. Min Act: -0.0002

Data Index: 182760 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6295. Min Act: -0.0002

Data Index: 879882 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6125. Min Act: -0.0002

Data Index: 28074 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6019. Min Act: -0.0002

Data Index: 1158557 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6509. Min Act: -0.0002

Data Index: 186676 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6424. Min Act: -0.0002

Data Index: 1268302 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.6085. Min Act: -0.0002

Data Index: 1047346 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.8715. Min Range: -1.8715

Max Act: 1.5920. Min Act: -0.0002

Data Index: 1341634 (C4 (Web Text))

Max Activating Token Index: 568